Teaching

Two graduate courses at Columbia University, High-Performance Machine Learning and the Scaling LLMs research seminar, and the Dataflow Architectures for AI specialization on Coursera with IBM Research.

Teaching Philosophy

Systems Thinking

Understanding how components interact at scale — from silicon to software stack. Students don't just learn algorithms; they implement them on real hardware and measure the results.

Empirical Rigor

Every claim must be measured and validated. Courses emphasize profiling, benchmarking, and performance analysis as first-class skills alongside theoretical foundations.

Ethical Awareness

Considering the societal implications of AI systems. The energy cost of training, the accessibility of deployment, and the responsibility of building technology that serves everyone.

Institution

Columbia University

Courses

2 Graduate

Focus

AI Systems & HPC

Approach

Research-Driven

In the Classroom

Teaching GPU Architecture at Columbia University

Teaching GPU Architecture at Columbia University

Lecture on Model Pruning — HPML at Columbia

Lecture on Model Pruning — HPML at Columbia

Guest Lecture at University of Sharjah

Guest Lecture at University of Sharjah

Student Voices

What students take away

A great semester in Scaling LLMs, and again in HPML — lucky to be taking these courses. Hoping to learn more and more in these fields over time.
Graduate student
Scaling LLMs & High-Performance Machine Learning
Columbia CTL Thank-a-Prof · 2026
Graduate Course

High-Performance Machine Learning

COMS E6998 · Columbia University

At the intersection of AI and High-Performance Computing, this course covers foundational and advanced techniques that drive efficient AI systems — from GPU programming and distributed training to LLM serving and model compression. Based on PyTorch and CUDA.

PyTorch & CUDA Programming
Distributed Training at Scale
LLM Serving (vLLM, PagedAttention)
Model Compression & Quantization

A frontier research seminar exploring scaling, optimizing, and deploying large language models through a structured progression from foundations to futures. Students present and critique top-tier papers (NeurIPS, ICML, ICLR, ISCA, ACL) and produce a survey paper with experimental evaluation.

Top-Tier Paper Critiques
Agentic AI & Multimodal Models
Hardware Futures (Analog, NorthPole)
Publish-Ready Survey Projects
Online Specialization

Dataflow Architectures for AI

Coursera · IBM Research

View on Coursera

A six-course specialization I teach for IBM Research, following a single PyTorch model as it runs across GPUs, Google TPUs, the Cerebras WSE, the Groq LPU, and IBM Spyre. It covers execution models, compilation, memory systems, debugging, and performance modeling through hands-on labs, and leads to a professional certificate in AI Systems Performance Engineering.

The Accelerator Landscape
Dataflow Execution Models
Compilation & Memory Systems
Debugging & Performance Modeling